© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 20200
    Prev
    Next
    INDEX
    Explanations

    phrases related to federal government activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the federal government

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ktop
    -0.95
    hots
    -0.73
    perse
    -0.70
    sbm
    -0.70
    zzo
    -0.69
    ventus
    -0.67
     Tycoon
    -0.67
    hops
    -0.67
    poke
    -0.66
    oko
    -0.66
    POSITIVE LOGITS
     government
    1.19
     judiciary
    1.00
    government
    0.95
     treasury
    0.91
     agency
    0.90
     agencies
    0.88
     Government
    0.85
    ists
    0.85
    ist
    0.84
     bureaucracy
    0.84
    Activations Density 0.027%

    No Known Activations